Novelty Search in Representational Space for Sample Efficient Exploration Ruo Y u Tao 1, 2, *, Vincent Franc ois-Lavet

We present a new approach for efficient exploration which leverages a low-dimensional encoding of the environment learned with a combination of model-based and model-free objectives. Our approach uses intrinsic rewards that are based on the distance of nearest neighbors in the low dimensional representational space to gauge novelty.